{"url":"/dataset/xwikiref","name":"XWikiRef","full_name":null,"description_markdown":"We provide a new data set XWikiRef for the task of Cross-lingual Multi-document Summarization. This task aims at generating Wikipedia style text in Low Resource languages by taking reference text as input. Overall, the data set contains 8 different languages: bengali (bn), english (en), hindi (hi), marathi (mr), malayalam (ml), odia (or), punjabi (pa) and tamil (ta). It also contains 5 domains: books, films, politicians, sportsman and writers.\r\n\r\n##Data Format\r\n\r\nDataset is publicly available [here](https://github.com/DhavalTaunk08/XWikiGen). Each directory contains language specific data subset having 1 json file per domain. In each file, each line denotes one article. It contains the following set of keys:\r\n\r\n- Article title\r\n- Sections\r\n    - section title 1\r\n    - section text 1\r\n    - list of reference texts 1\r\n    - .....\r\n    - .....\r\n    - .....\r\n    - section title n\r\n    - section text n\r\n    - list of reference texts 1","description_withheld":null,"homepage":"https://github.com/DhavalTaunk08/XWikiGen","introduced_date":"2023-03-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/xwikigen-cross-lingual-summarization-for","title":"XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages","first_author":"Dhaval Taunk","url":null},"license":{"name":"MIT License","url":"https://github.com/DhavalTaunk08/XWikiGen/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Cross-Lingual Abstractive Summarization","url":"/task/cross-lingual-abstractive-summarization","datasets_with_task":"/datasets/task/cross-lingual-abstractive-summarization"},{"name":"Unsupervised Extractive Summarization","url":"/task/unsupervised-extractive-summarization","datasets_with_task":"/datasets/task/unsupervised-extractive-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Malayalam","url":"/datasets/language/malayalam"},{"name":"Odia","url":"/datasets/language/odia"},{"name":"Punjabi","url":"/datasets/language/punjabi"}],"variants":["XWikiRef"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}